Model: GELU Model: 2 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1375 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.4507. Min Range: -3.4507

Max Act: 3.4507. Min Act: -0.1700

Data Index: 166150 (C4 (Web Text))

Max Activating Token Index: 688

Text #1

Max Range: 3.4507. Min Range: -3.4507

Max Act: 3.3566. Min Act: -0.1700

Data Index: 1209058 (C4 (Web Text))

Max Activating Token Index: 383

Text #2

Max Range: 3.4507. Min Range: -3.4507

Max Act: 3.3566. Min Act: -0.1700

Data Index: 534717 (C4 (Web Text))

Max Activating Token Index: 110

Text #3

Max Range: 3.4507. Min Range: -3.4507

Max Act: 3.3723. Min Act: -0.1700

Data Index: 1281845 (C4 (Web Text))

Max Activating Token Index: 307

Text #4

Max Range: 3.4507. Min Range: -3.4507

Max Act: 3.3566. Min Act: -0.1700

Data Index: 43133 (C4 (Web Text))

Max Activating Token Index: 249

Text #5

Max Range: 3.4507. Min Range: -3.4507

Max Act: 3.3252. Min Act: -0.1700

Data Index: 980791 (C4 (Web Text))

Max Activating Token Index: 839

Text #6

Max Range: 3.4507. Min Range: -3.4507

Max Act: 3.3095. Min Act: -0.1700

Data Index: 735744 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 3.4507. Min Range: -3.4507

Max Act: 3.3095. Min Act: -0.1700

Data Index: 927422 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 3.4507. Min Range: -3.4507

Max Act: 3.2938. Min Act: -0.1700

Data Index: 664268 (C4 (Web Text))

Max Activating Token Index: 861

Text #9

Max Range: 3.4507. Min Range: -3.4507

Max Act: 3.3409. Min Act: -0.1700

Data Index: 420046 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 3.4507. Min Range: -3.4507

Max Act: 3.2781. Min Act: -0.1700

Data Index: 1016220 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 3.4507. Min Range: -3.4507

Max Act: 3.2938. Min Act: -0.1700

Data Index: 630421 (C4 (Web Text))

Max Activating Token Index: 229

Text #12

Max Range: 3.4507. Min Range: -3.4507

Max Act: 3.3095. Min Act: -0.1700

Data Index: 407912 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 3.4507. Min Range: -3.4507

Max Act: 3.2938. Min Act: -0.1700

Data Index: 45265 (C4 (Web Text))

Max Activating Token Index: 565

Text #14

Max Range: 3.4507. Min Range: -3.4507

Max Act: 3.2781. Min Act: -0.1700

Data Index: 1259369 (C4 (Web Text))

Max Activating Token Index: 229

Text #15

Max Range: 3.4507. Min Range: -3.4507

Max Act: 3.2624. Min Act: -0.1700

Data Index: 428189 (C4 (Web Text))

Max Activating Token Index: 491

Text #16

Max Range: 3.4507. Min Range: -3.4507

Max Act: 3.2781. Min Act: -0.1700

Data Index: 733059 (C4 (Web Text))

Max Activating Token Index: 359

Text #17

Max Range: 3.4507. Min Range: -3.4507

Max Act: 3.2781. Min Act: -0.1700

Data Index: 1185659 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 3.4507. Min Range: -3.4507

Max Act: 3.2781. Min Act: -0.1700

Data Index: 609258 (C4 (Web Text))

Max Activating Token Index: 297

Text #19

Max Range: 3.4507. Min Range: -3.4507

Max Act: 3.2781. Min Act: -0.1700

Data Index: 840382 (C4 (Web Text))

Max Activating Token Index: 266